FreeBSD source tree https://cgit-dev.freebsd.org/src-test2/atom?h=release%2F11.4.0 2019-05-12T12:30:45Z 2019-05-12T12:30:45Z Andriy Voskoboinyk avos@FreeBSD.org 2019-05-12T12:30:45Z urn:sha1:c2540bd39b5de69a3f8b3863c28d0ac0e11d484d urtw(4), otus(4), iwi(4): allow to set non-default MAC address via ifconfig(8) Was tested with Netgear WG111 v3 (RTL8187B, urtw(4)), STA mode. 2019-03-28T09:50:25Z Andriy Voskoboinyk avos@FreeBSD.org 2019-03-28T09:50:25Z urn:sha1:878318d26bdecded9654efbf90104bbab93ebd63 Fix ieee80211_radiotap(9) usage in wireless drivers: - Alignment issues: * Add missing __packed attributes + padding across all drivers; in most places there was an assumption that padding will be always minimally suitable; in few places - e.g., in urtw(4) / rtwn(4) - padding was just missing. * Add __aligned(8) attribute for all Rx radiotap headers since they can contain 64-bit TSF timestamp; it cannot appear in Tx radiotap headers, so just drop the attribute here. Refresh ieee80211_radiotap(9) man page accordingly. - Since net80211 automatically updates channel frequency / flags in ieee80211_radiotap_chan_change() drop duplicate setup for these fields in drivers. 2018-03-07T10:54:10Z Eitan Adler eadler@FreeBSD.org 2018-03-07T10:54:10Z urn:sha1:909fc04f4888e37d7e0faf2993b24e1709e87ea1 These commits have KPI/KBI considerations (or are a result of those that do). I did not properly take into account these concerns when merging to a kbi-stable branch. Requested by: jhb Pointyhat to: eadler 2018-03-05T07:58:48Z Eitan Adler eadler@FreeBSD.org 2018-03-05T07:58:48Z urn:sha1:90d88e3c631164fd404f1f6f3427ec3474e9c394 net80211: convert all ieee80211_input_mimo*() consumers to ieee80211_add_rx_params() + drop last (ieee80211_rx_stats) parameter Note: there is an additional check for ieee80211_get_rx_params() return value (which does not exist in the original diff). 2018-03-05T07:54:57Z Eitan Adler eadler@FreeBSD.org 2018-03-05T07:54:57Z urn:sha1:6eb8d9ef1bf27243090ae4d5748e2be756e4873d [net80211] extend the ieee80211_rx_stats struct to include more information. There are a variety of more interesting RX statistics that we should keep track of but we don't. This is a starting point for adding more information. Specifically: * now the RX rate information and some of the packet status is passed up; * The 32 bit or 64 bit TSF is passed up; * the PHY mode is passed up; * the "I'm decap'ed AMSDU!" state is passed up; * number of RX chains is bumped to 4. This is all mostly a placeholder for getting the data into the RX status before we pass it up to net80211 - unfortunately we don't yet enforce that drivers provide it, nor do we pass the provided info back up the stack so anyone can use the data. We're going to need to use some of this data moving forward. Notably, now that some hardware can do AMSDU decap for us (the intel iwm driver can do it when we flip it on; the ath10k port I'm doing does it for us) then we need to pass it up through the stack so the duplicate RX sequence numbers and crypto/IV details don't cause the packet to be dropped and/or counted against a replay counter. It's also the beginning of being able to do more interesting node accounting in net80211. Specifically, once drivers start populating per-packet rate information, AMPDU information, timestamps, etc, we can start providing histograms of rate-versus-RSSI, account for receive time spent per node and other such interesting things. (Note: I'm also hoping to include ranging and RTT information for future chipset support; and it's likely going to include it in this kind of fashion.) 2016-05-09T19:28:22Z Pedro F. Giffuni pfg@FreeBSD.org 2016-05-09T19:28:22Z urn:sha1:9be4c8d056255c6a1367fe77748b62c4680af8a9 Bump the OpenBSD revision tag since the corresponding changes don't apply to us and drop an unnecessary header. No functional change. 2016-05-02T05:43:46Z Adrian Chadd adrian@FreeBSD.org 2016-05-02T05:43:46Z urn:sha1:b35978d0da3992f6878ea37e50b7126320ceea20 * break out the operating mode and rx filter into new functions, rather than them being hard-coded * if we're in sniffer mode or not associated, set the BSS MAC to all zero, rather than relying on a chip reset to do it for us * add comments about .. how interestingly buggy the chip is. Tested: * AR9170 + AR9102, STA+monitor mode Obtained from: linux carl9170 (general chip workings, constant definitions) 2016-05-01T18:15:40Z Andriy Voskoboinyk avos@FreeBSD.org 2016-05-01T18:15:40Z urn:sha1:7f145aba97891ca4ad19d9f6f55a24730972ad7a - Use device's channel list instead of default one (from ieee80211_init_channels()). - Sort channels (ieee80211_add_channel_list_* requirement). - Add ic_getradiocaps() method. Added channels: 2GHz band: 12, 13 and 14. 5GHz band: 34, 38, 42, 46 and 165. Reviewed by: adrian Differential Revision: https://reviews.freebsd.org/D6145 2016-04-29T22:14:11Z Andriy Voskoboinyk avos@FreeBSD.org 2016-04-29T22:14:11Z urn:sha1:a061fea6eeb689ab01affff1350cc47beb4a0ce5 Auto-replace 'howmany(IEEE80211_MODE_MAX, 8)' with 'IEEE80211_MODE_BYTES'. No functional changes. 2016-04-20T18:29:30Z Andriy Voskoboinyk avos@FreeBSD.org 2016-04-20T18:29:30Z urn:sha1:31021a2b4ef82d6491e5769defa8b34f16437761 le*dec / le*enc functions. Replace net80211 specific macros with system-wide bytestream encoding/decoding functions: - LE_READ_2 -> le16dec - LE_READ_4 -> le32dec - LE_WRITE_2 -> le16enc - LE_WRITE_4 -> le32enc + drop ieee80211_input.h include, where it was included for these operations only. Reviewed by: adrian Differential Revision: https://reviews.freebsd.org/D6030